AI Workbench offers two notebooks for predicting customer churn: Predict Propensity to Churn, which calculates churn probability, and Analyze Propensity to Churn, which evaluates churn predictions based on customer segments.
Use the Predict Propensity to Churn notebook—no coding required—to estimate churn likelihood for a selected customer segment. The model writes a churn score to each customer profile. It can also predict attrition based on categorical properties like gender, creating separate models for different groups. The notebook leverages an AI time-to-event model to analyze customer data.
Before you begin, make sure you have customer contract or subscription start and end dates stored in BlueConic profile properties.
Add a Predict propensity to churn notebook
Navigate to More > AI Workbench > Add notebook.
Choose RFM notebook from the pop-up window.
Give your notebook a name.
Save your settings.
Set the Predict propensity to churn notebook parameters
Select the Parameters tab.
Select a customer segment for the Applied segment—this is where the churn prediction model will be trained and applied. For optimal performance, choose the smallest relevant segment.
Select profile properties for contract start and end dates in date-time format.
(Optional) To split the segment into groups, select a categorical property. The model will compare profiles based on this property's values, with a limit of 10 categories for performance reasons.
Select or create a churn probability profile property to save the notebook's output, the probability that a profile will churn.
(Optional) Adjust the maximum profiles the model examines. Higher numbers improve accuracy but increase processing costs. Use 0 to include all profiles in the segment.
(Optional) You can change the propensity to churn model and color map used to display your results. Options include:
Save your settings.
Run the Predict propensity to churn notebook
Select the Schedule and run history tab.
Click Run now to run the notebook analysis manually.
To schedule the import and export for a future date, activate Enable scheduling.
Click the Settings icon to select how to schedule the notebook by choosing an option from the drop-down list.
Set a time for the import. Click OK.
Save your settings.
View your results
When you run the Propensity to churn notebook, a preview window opens with your results for relevant sections of the code or notebook cells. This notebook also writes the churn probability to each profile it evaluates, in the profile property you selected. You can use this information to target or segment profiles with offers to prevent churn.
Next steps
Use the companion AI notebook, Analyze propensity to churn, to examine how churn risk compares between different customer segments.